检索结果-内蒙古大学图书馆

Completed Interaction Networks for Pedestrian Trajectory Prediction

IEEE Transactions on Multimedia 2025年

作者： Zhang, Zhong Zhou, Jianglin Liu, Shuang Xiao, Baihua Tianjin Normal University Tianjin Key Laboratory of Wireless Mobile Communications and Power Transmission Tianjin300387 China Chinese Academy of Sciences State Key Laboratory for Management and Control of Complex Systems Institute of Automation Beijing100190 China

The social and environmental interactions, as well as the pedestrian goal are crucial for pedestrian trajectory prediction. This is because they could learn both complex interactions in the scenes and the intentions of the pedestrians. However, most existing methods either learn the one-moment social interactions, or supervise the pedestrian trajectories using long-term goal, resulting in suboptimal prediction performances. In this paper, we propose a novel network named Completed Interaction Network (CINet) to simultaneously consider the social interactions in all moments, the environmental interactions and the short-term goal of pedestrians in a unified framework for pedestrian trajectory prediction. Specifically, we propose the Spatio-Temporal Transformer Layer (STTL) to fully mine the spatio-temporal information among historical trajectories of all pedestrians in order to obtain the social interactions in all moments. Additionally, we present the Gradual Goal Module (GGM) to capture the environmental interactions under the supervision of the short-term goal, which is beneficial to understanding the intentions of the pedestrian. Afterwards, we employ the cross-attention to effectively integrate the all-moment social and environmental interactions. The experimental results on three standard pedestrian datasets, i.e., ETH/UCY, SDD and inD demonstrate that our method achieves a new state-of-the-art performance. Furthermore, the visualization results indicate that our method could predict trajectories more reasonably in complex scenarios such as sharp turns, infeasible areas and so on. © 1999-2012 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Development of an Industrial Real-time Ethernet Protocol Stack Based on SoC

Development of an Industrial Real-time Ethernet Protocol Sta...

引用

2022 International Symposium on Networks, computers and Communications, ISNCC 2022

作者： Zhang, Bo Yan, Bingjun Liu, Mingzhe Hu, Bo Xu, Aidong Wang, Kai Key Laboratory of Networked Control Systems Chinese Academy of Sciences China Shenyang Institute of Automation Chinese Academy of Sciences China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences China

ISBN: (数字)9781665485449

ISBN: (纸本)9781665485449

In order to improve the real-time and reliability of network communication in intelligent ship system, this paper analyzes the requirements of ship-borne network, and develops a real-time Ethernet protocol stack based on Zynq7000 series SoC chip. The development of the protocol stack includes the software layer and the firmware layer. As the main part of the protocol stack, the software layer adds real-time communication entities upon the data link layer of the Ethernet reference model, and the timing of communication is controlled by the synchronous precise measurement clock to realize the real-time scheduling and transmission of data. On the other hand, the PTP message timestamp function of clock synchronization and the redundant function of zero recovery time based on PRP algorithm is realized on the firmware layer. Finally, the real-time, reliability and synchronization accuracy of the protocol stack are tested and verified on the developed real-time Ethernet cards. © 2022 IEEE.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Text-guided attention is all you need for zero-shot robustness in vision-language models 24

Text-guided attention is all you need for zero-shot robustne...

引用

Proceedings of the 38th International Conference on Neural Information Processing systems

作者： Lu Yu Haiyang Zhang Changsheng Xu School of Computer Science and Engineering Tianjin University of Technology State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation University of Chinese Academy of Sciences

ISBN: (纸本)9798331314385

Due to the impressive zero-shot capabilities, pre-trained vision-language models (e.g. CLIP), have attracted widespread attention and adoption across various domains. Nonetheless, CLIP has been observed to be susceptible to adversarial examples. Through experimental analysis, we have observed a phenomenon wherein adversarial perturbations induce shifts in text-guided attention. Building upon this observation, we propose a simple yet effective strategy: Text-Guided Attention for Zero-Shot Robustness (TGA-ZSR). This framework incorporates two components: the Attention Refinement module and the Attention-based Model Constraint module. Our goal is to maintain the generalization of the CLIP model and enhance its adversarial robustness: The Attention Refinement module aligns the text-guided attention obtained from the target model via adversarial examples with the text-guided attention acquired from the original model via clean examples. This alignment enhances the model's robustness. Additionally, the Attention-based Model Constraint module acquires text-guided attention from both the target and original models using clean examples. Its objective is to maintain model performance on clean samples while enhancing overall robustness. The experiments validate that our method yields a 9.58% enhancement in zero-shot robust accuracy over the current state-of-the-art techniques across 16 datasets. Our code is available at https://***/zhyblue424/TGA-ZSR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AUTOSIM:Automated Urban Traffic Operation Simulation via Meta-Learning

引用

IEEE/CAA Journal of Automatica Sinica 2023年第9期10卷 1871-1881页

作者： Yuanqi Qin Wen Hua Junchen Jin Jun Ge Xingyuan Dai Lingxi Li Xiao Wang Fei-Yue Wang Zhejiang Lab Hangzhou 310030China ECARX Technology Co. Ltd.Shanghai 201811China IEEE Zhejiang Supcon Information Company Ltd. Hangzhou 310052China the State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Indiana University-Purdue University Indianapolis(IUPUI) IndianapolisIndiana 46202 USA School of Artificial Intelligence Anhui UniversityHefei 230039China

Online traffic simulation that feeds from online information to simulate vehicle movement in real-time has recently seen substantial advancement in the development of intelligent transportation systems and urban traffic *** has been a challenging problem due to three aspects:1)The diversity of traffic patterns due to heterogeneous layouts of urban intersections;2)The nature of complex spatiotemporal correlations;3)The requirement of dynamically adjusting the parameters of traffic models in a real-time *** cater to these challenges,this paper proposes an online traffic simulation framework called automated urban traffic operation simulation via meta-learning(AUTOSIM).In particular,simulation models with various intersection layouts are automatically generated using an open-source simulation tool based on static traffic geometry *** a meta-learning technique,AUTOSIM enables an automated learning process for dynamic model settings of traffic scenarios featured with different spatiotemporal ***,AUTOSIM is capable of adapting traffic model parameters according to dynamic traffic information in real-time by using a *** computational experiments,we demonstrate the effectiveness of the meta-learningbased framework that is capable of providing reliable supports to real-time traffic simulation and dynamic traffic operations.

关键词： Conditional generative adversarial network signalized urban networks short-term link speed prediction

来源：评论

学校读者我要写书评

暂无评论

THE PARAMETER SENSITIVITY ANALYSIS ON THE DYNAMIC STIFFNESS OF THE ELECTRO-HYDROSTATIC ACTUATOR

THE PARAMETER SENSITIVITY ANALYSIS ON THE DYNAMIC STIFFNESS ...

引用

2024 CSAA/IET International Conference on Aircraft Utility systems, AUS 2024

作者： Renlei, Wei Shuai, Wu Bing, Chu Yuliang, Yang Jianing, Luo School of Automation Science and Electrical Engineering Beihang University Beijing100191 China National Key Laboratory of Aircraft Integrated Flight Control Beihang University Beijing100191 China Key Laboratory of Advanced Aircraft Systems Beihang University Ministry of Industry and Information Technology Beijing100191 China Ningbo Institute of Technology Beihang University Ningbo315800 China Tianmushan Laboratory Hangzhou310023 China AVIC Shenyang Aircraft Design and Research Institute Shenyang110035 China

The electro-hydrostatic actuator (EHA) has the advantage of high power weight ratio, less leakage and the absence of throttle loss. It's used on the multi-electric aircraft and the all-electric aircraft. However, it will be affected by the aerodynamic load and the rudder flutter will occur if the dynamic stiffness of the EHA is low. As a result, it's significant to analyse the sensitivity of the EHA's parameters on the dynamic stiffness. The article builds a linear model of the EHA considering the leakage in the system. What's more, the local parameter sensitivity for the dynamic stiffness is calculated when the frequency is between 0.01 Hz and 1000 Hz. © The Institution of Engineering & Technology 2024.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Low-rank Adaptation Method for Wav2vec2-based Fake Audio Detection

Low-rank Adaptation Method for Wav2vec2-based Fake Audio Det...

引用

2023 Workshop on Deepfake Audio Detection and Analysis, DADA 2023

作者： Wang, Chenglong Yi, Jiangyan Zhang, Xiaohui Tao, Jianhua Yan, Xinrui Xu, Le Fu, Ruibo University of Science and Technology of China Hefei China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijng China School of Artificial Intelligence University of Chinese Academy of Sciences China School of Computer and Information Technology Beijing Jiaotong University China Department of Automation Tsinghua University China

Self-supervised speech models are a rapidly developing research topic in fake audio detection. Many pre-trained models can serve as feature extractors, learning richer and higher-level speech features. However,when fine-tuning pre-trained models, there is often a challenge of excessively long training times and high memory consumption, and complete fine-tuning is also very expensive. To alleviate this problem, we apply low-rank adaptation(LoRA) to the wav2vec2 model, freezing the pre-trained model weights and injecting a trainable rank-decomposition matrix into each layer of the transformer architecture, greatly reducing the number of trainable parameters for downstream tasks. Compared with fine-tuning with Adam on the wav2vec2 model containing 317M training parameters, LoRA achieved similar performance by reducing the number of trainable parameters by 198 times. © 2023 CEUR-WS. All rights reserved.

关键词： Fake detection

来源：评论

学校读者我要写书评

暂无评论

SIM: A Scenario IMagination Based Deep Reinforcement Learning Method for Outdoor Transportation Environment Exploration 11

SIM: A Scenario IMagination Based Deep Reinforcement Learnin...

引用

11th IEEE Data Driven control and Learning systems Conference, DDCLS 2022

作者： Li, Haoran Zhang, Qichao Chen, Yaran Zhao, Dongbin State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100190 China Peng Cheng Laboratory Shenzhen518000 China

ISBN: (数字)9781665496759

ISBN: (纸本)9781665496759

Autonomous exploration is very important for robotics, especially for mapping, navigation, and planning in an unknown environment. In recent years, automatic exploration methods in the indoor environment have been extensively studied, but there is little research on exploration in the outdoor transportation environment. Due to the limitations of outdoor traffic rules and the scale of the environment, the methods for the indoor environment are difficult to apply to the transportation environment. Aiming at exploration in the transportation environment, this paper proposes a deep reinforcement learning algorithm based on Scenario IMagination(SIM), which has two important components: 1) a mid-level action space, which combines the classical robot control algorithm, addressing the inefficient learning and unstable navigation of deep reinforcement learning algorithms in automatic exploration. With this action space, the deep reinforcement learning algorithm achieves excellent exploration performance in both normal scale environments and large-scale branchless environments;2) a scenarios buffer, which relieves hard exploration problems of deep reinforcement learning due to serious imbalances of samples in large-scale multibranch scenarios. Compared to the map-less navigation approaches, SIM achieves excellent exploration performance in large-scale multi-branch environments. © 2022 IEEE.

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

3D Vision Based Lamination Gap Detection of Carbon Fiber Composite

3D Vision Based Lamination Gap Detection of Carbon Fiber Com...

引用

2023 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2023

作者： Xu, Yuanye Yuan, Libiao Liang, Wei Yang, Yutuo Liu, Shuai Zeng, Ziming Zhang, Yinlong Shenyang Institute of Automation Chinese Academy of Sciences Key Laboratory of Networked Control Systems Shenyang110016 China Shenyang University of Chemical Technology College of Information Engineering Shenyang110142 China Shenzhen Polytechnic School of Automotive and Transportation Engineering Shenzhen518055 China

ISBN: (纸本)9798350327182

The paper presents a machine learning approach to detect laminate gaps and to classify them as open or closed. Compared with the traditional detection methods, which suffer from low precision of point cloud segmentation and poor effect of gap extraction in traditional gap detection, this paper proposes a gap detection algorithm based on 3D Vision. First, an improved undirected graph point cloud segmentation algorithm is used to overcome the under-segmentation of the target region. Second, an adaptive vector for angle discriminant model is proposed to solve the problem of poor extraction effect of the gap edge points. Finally, the B-spline curve-fitting model is used to describe the 3D points on the lamination edges. The proposed algorithm has been evaluated in a visual quality detection platform for carbon fiber composite laminates. The results show that the proposed approach is able to accurately detect and classify laminate gaps in carbon fiber composite structures, providing a reliable tool for quality control in industrial manufacturing processes. © 2023 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Dynamic Stiffness Analysis and Parameter Optimization of Digital Electro-Hydraulic Actuator 9

Dynamic Stiffness Analysis and Parameter Optimization of Dig...

引用

9th International Conference on Fluid Power and Mechatronics, FPM 2023

作者： Zhao, Tian-Yu Wu, Shuai Li, Wen-Ding Li, Ren-Jie Wang, Yi Song, Bing Fu, Jun-Yong Jiao, Zong-Xia School of Automation Science and Electrical Engineering Beihang University Beijing China Research Institute for Frontier Science Beihang University Beijing China Ningbo Institute of Technology Beihang University Ningbo China Shanghai Aerospace Control Technology Institute Shanghai China Shanghai Servo-system Engineering Research Center Shanghai China Beihang University Key Laboratory of Advanced Airborne Systems Beijing China Beihang University Science and Technology on Aircraft Control Laboratory Beijing China Tianmushan Laboratory Hangzhou China

ISBN: (数字)9798350304947

ISBN: (纸本)9798350304947

In this paper, the dynamic stiffness characteristics of digital electro-hydraulic actuator are analyzed, and the influence of the introduction of digital valve on the electro-hydraulic actuator is studied. Based on the actual working conditions and requirements of digital electro-hydraulic actuator, the dynamic stiffness models of digital electro-hydraulic actuator and servo valve controlled electro-hydraulic actuator are established respectively. Two testing methods were used to complete closed-loop dynamic stiffness simulation, and the digital valve control system and the servo valve control system are compared and analyzed. By changing different system parameters, the sensitivity analysis of dynamic stiffness parameters of digital electro-hydraulic actuator is realized. Finally, the optimization of system control parameters is realized, and the optimization direction of the system parameters of the digital electro-hydraulic actuator is provided. © 2023 IEEE.

关键词： Stiffness

来源：评论

学校读者我要写书评

暂无评论

CPL-CLIP: Compound Prompt Learning for Flexible-Modal Face Anti-Spoofing 18

CPL-CLIP: Compound Prompt Learning for Flexible-Modal Face A...

引用

18th IEEE International Joint Conference on Biometrics, IJCB 2024

作者： Zhang, Ying Zhu, Xiangyu Liu, Ajian Lin, Xun Wan, Jun Zhang, Jing Lei, Zhen Beihang University School of Computer Science and Engineering China Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation China University of Chinese Academy of Sciences School of Artificial Intelligence China Macau University of Science and Technology School of Computer Science and Engineering China Chinese Academy of Sciences Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation China

ISBN: (纸本)9798350364132

Face anti-spoofing (FAS) is pivotal in safeguarding the integrity of face recognition systems. Flexible-modal FAS utilizes multi-modal data and trains a unified model adaptable to any single-modal testing scenario. This innovation addresses the shortcomings of conventional multi-modal FAS approaches, which typically demand separate model training and deployment for each modality. However, existing flexible-modal FAS approaches activate specific network branches based on the modality of the tested sample. This not only increases the model's parameters but also necessitates the provision of the image's modality for testing, thereby constraining deployment flexibility. To address the issue, we present Compound Prompt Learning CLIP (CPL-CLIP), a novel method for flexible-modal FAS. This approach capitalizes on a learned textual prompt that is nearly independent of modality, thus bolstering class-based classification across arbitrary modalities. Specifically, our CPL-CLIP introduces a Dual-Branch Prompt (DBP), consisting of class and modal prompts that describe and guide classification, where each prompt is composed of learnable vectors and fixed templates. To further render the class prompt as modality-agnostic as possible, a Cosine Similarity Loss (CSL) is proposed to facilitate the maximal separation of the class prompt from the modality prompt. With only the class prompt utilized during testing, CPL-CLIP enables deployment in diverse modal testing scenarios without the necessity of the test image's modality to be known. Extensive experiments demonstrate CPL-CLIP's superiority over existing methods on several flexible-modal FAS benchmarks. © 2024 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：